Unlock instant, AI-driven research and patent intelligence for your innovation.

A Method of Radar Image Difference Detection Based on Feedback and Iteration

A difference detection and radar image technology, applied in the field of radar image difference detection based on feedback and iteration, can solve problems such as difficulties and high cost of difference images, and achieve accurate results

Active Publication Date: 2020-02-07
UNIV OF SCI & TECH OF CHINA
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although supervised methods generally have better detection results than unsupervised algorithms, the cost of producing labeled difference images is relatively high and it is relatively difficult.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Method of Radar Image Difference Detection Based on Feedback and Iteration
  • A Method of Radar Image Difference Detection Based on Feedback and Iteration
  • A Method of Radar Image Difference Detection Based on Feedback and Iteration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The specific implementation of the present invention will be described in detail below with reference to the accompanying drawings.

[0026] Such as figure 1 As shown, the specific steps of the method of the present invention include Step 1-4:

[0027] Step1. Difference map generation: For a given SAR image taken at different times in the same area, first use a difference map generation function to generate a difference map (DI); the parameters of the difference map generation function include filter weight parameters.

[0028] Given two SAR images I 1 And I 2 , First perform PPB filtering, then consider the neighborhood information of each point to generate a difference map:

[0029]

[0030] m represents the index of the pixel, DI represents the difference map, DI(m) represents the difference of the point, ω m Represents the neighborhood around m, Represents the filtering weight of the t-th iteration, t represents the number of iterations, I 1 (i) means I 1 Gray value of mid...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a feedback and iteration-based radar image difference detecting method. Aiming at two main steps of difference image generation and binary calibration according to differenceimages in a conventional method, the method comprises the step of by adopting results of the binary calibration as bases of feedback, adjusting function parameters of the difference image generation and the threshold setting of the binary calibration. The method disclosed by the invention has the advantages that the results tend to be accurate through iteration; in the meantime, the modes of the difference image generation and the binary calibration at different positions in the images are different through considering the local information of the images, so that the robustness of an algorithmis increased and the detecting accuracy can be increased to a certain degree; and an MRF (Markov Random Filed) function serves as a termination condition of the iteration in the detecting method, sothat the accuracy of the detecting method is further guaranteed to a certain degree.

Description

Technical field [0001] The invention relates to data image processing, in particular to a radar image difference detection method based on feedback and iteration. Background technique [0002] In recent years, with the rapid development of computer technology, image-based information acquisition and analysis rely more and more on computer technology. The image difference detection based on computer vision is also one of the research hotspots in recent years. This project mainly solves the problem of detecting the difference of SAR images without supervision. As the name suggests, image difference detection is to detect and label the differences in two basically identical images. One of the important applications is the analysis of radar images. Change detection can be used for environmental change detection, landform survey, forest vegetation change and so on. This difference detection mainly needs to analyze two radar images of the same area at different times. [0003] The c...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/80
CPCG06T7/0002G06T7/80G06T2207/10044
Inventor 凌强赵敏达李峰
Owner UNIV OF SCI & TECH OF CHINA